© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207049
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     +#
    0.43
    胥
    0.42
     #"
    0.41
     #
    0.40
    asti
    0.39
    ouvrage
    0.39
    wci
    0.39
    wen
    0.38
     saint
    0.38
     \#
    0.38
    POSITIVE LOGITS
    である
    0.40
     attacking
    0.40
     만
    0.38
     багато
    0.38
    ਹ
    0.37
     어
    0.37
    atta
    0.36
     акт
    0.36
    OscInitStruct
    0.36
     છે
    0.34
    Activations Density 0.001%

    No Known Activations